A function used by the train function in order to conduct backpropagation.
backprop_evaluate(parameters, dat, truth, net, loss, batchsize, dropout)the derivative of the cost function with respect to each of the parameters
network weights and bias parameters as a vector
the input data, a list of vectors
the truth, a list of vectors to compare with output from the feed-forward network
an object of class network, see ?network
the loss function, see ?Qloss and ?multinomial
optional batchsize argument for use with stochastic gradient descent
optional list of dropout probabilities ?dropoutProbs
Ian Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach. Deep Learning. (2016)
Terrence J. Sejnowski. The Deep Learning Revolution (The MIT Press). (2018)
Neural Networks YouTube playlist by 3brown1blue: https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
http://neuralnetworksanddeeplearning.com/
network, train, backprop_evaluate, MLP_net, backpropagation_MLP, logistic, ReLU, smoothReLU, ident, softmax, Qloss, multinomial, NNgrad_test, weights2list, bias2list, biasInit, memInit, gradInit, addGrad, nnetpar, nbiaspar, addList, no_regularisation, L1_regularisation, L2_regularisation